Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden, and it discloses key behaviors: the edit is committed to the same design_id as a versioned diff, not a new file; non-text properties are preserved; the heavy image is not moved; the box does not resize; and copy beyond roughly ±10% character count will overflow and require manual fixes. It also reveals that reusing a version tag is refused and that a real commit message is required.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured and front-loaded with the main action, followed by behavioral constraints and usage precautions. Each paragraph earns its place, though phrases like 'the browser courier' and 'the store is configuration management' are somewhat jargon-heavy and may require extra inference.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with seven parameters, no annotations, and an output schema, the description is relatively complete: it explains what happens to the design, how versioning works, the most important editing constraint, and where to get needed reference data. It does not elaborate on authentication/billing parameters, but those are standard and covered by the schema, and the output schema exists to describe return values.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is high at 86%, so the description does not need to restate parameters. It adds meaningful semantic constraints beyond the schema, especially the ±10% character-count guidance tied to the get_design_text `chars` field, and it clarifies that edits are applied to the same design_id rather than creating a design copy.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Apply text edits to a stored design and commit a new version of it.' It distinguishes itself from other design tools by emphasizing that only words change while fonts, layout, and images are preserved, and that edits commit to the same design_id rather than creating a new file.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear usage context: it is for editing text inside an existing design while preserving visual assets, and it references related tools like get_design_text and roastify_list_design_versions for needed inputs. It does not explicitly name alternatives or say 'use X instead,' but the scope is clear and it warns about character-count limits that should guide when edits are appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.